agora inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH v7] Fix orderby handling in postgres_fdw
309+ messages / 2 participants
[nested] [flat]

* [PATCH v7] Fix orderby handling in postgres_fdw
@ 2021-09-06 07:54  Ronan Dunklau <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Ronan Dunklau @ 2021-09-06 07:54 UTC (permalink / raw)

The logic for pushing down order bys in postgres fdw didn't take into
account the specific operator used, and as such a pushed-down order by
could return wrong results.
---
 contrib/postgres_fdw/deparse.c                | 156 +++++++++++++-----
 .../postgres_fdw/expected/postgres_fdw.out    |  23 +++
 contrib/postgres_fdw/postgres_fdw.c           |  28 ++--
 contrib/postgres_fdw/postgres_fdw.h           |  11 +-
 contrib/postgres_fdw/sql/postgres_fdw.sql     |   8 +
 src/backend/optimizer/path/equivclass.c       |  26 ++-
 src/include/optimizer/paths.h                 |   2 +
 7 files changed, 187 insertions(+), 67 deletions(-)

diff --git a/contrib/postgres_fdw/deparse.c b/contrib/postgres_fdw/deparse.c
index d98bd66681..fb1b5f9d9b 100644
--- a/contrib/postgres_fdw/deparse.c
+++ b/contrib/postgres_fdw/deparse.c
@@ -37,9 +37,11 @@
 #include "access/sysattr.h"
 #include "access/table.h"
 #include "catalog/pg_aggregate.h"
+#include "catalog/pg_amop.h"
 #include "catalog/pg_collation.h"
 #include "catalog/pg_namespace.h"
 #include "catalog/pg_operator.h"
+#include "catalog/pg_opfamily.h"
 #include "catalog/pg_proc.h"
 #include "catalog/pg_type.h"
 #include "commands/defrem.h"
@@ -47,6 +49,7 @@
 #include "nodes/nodeFuncs.h"
 #include "nodes/plannodes.h"
 #include "optimizer/optimizer.h"
+#include "optimizer/paths.h"
 #include "optimizer/prep.h"
 #include "optimizer/tlist.h"
 #include "parser/parsetree.h"
@@ -182,6 +185,8 @@ static void deparseRangeTblRef(StringInfo buf, PlannerInfo *root,
 							   Index ignore_rel, List **ignore_conds, List **params_list);
 static void deparseAggref(Aggref *node, deparse_expr_cxt *context);
 static void appendGroupByClause(List *tlist, deparse_expr_cxt *context);
+static void appendOrderBySuffix(Oid sortop, Oid sortcoltype, bool nulls_first,
+								deparse_expr_cxt *context);
 static void appendAggOrderBy(List *orderList, List *targetList,
 							 deparse_expr_cxt *context);
 static void appendFunctionName(Oid funcid, deparse_expr_cxt *context);
@@ -1037,6 +1042,41 @@ is_foreign_param(PlannerInfo *root,
 	return false;
 }
 
+/*
+ * Returns true if it's safe to push down a sort as described by 'pathkey' to
+ * the foreign server
+ */
+bool
+is_foreign_pathkey(PlannerInfo *root,
+				   RelOptInfo *baserel,
+				   PathKey *pathkey)
+{
+	EquivalenceClass *pathkey_ec = pathkey->pk_eclass;
+	PgFdwRelationInfo *fpinfo = (PgFdwRelationInfo *) baserel->fdw_private;
+	Expr	   *em_expr;
+
+	/*
+	 * is_foreign_expr would detect volatile expressions as well, but checking
+	 * ec_has_volatile here saves some cycles.
+	 */
+	if (pathkey_ec->ec_has_volatile)
+		return false;
+
+	/* can't push down the sort if the pathkey's opfamily is not shippable */
+	if (!is_shippable(pathkey->pk_opfamily, OperatorFamilyRelationId, fpinfo))
+		return false;
+
+	em_expr = find_em_expr_for_rel(pathkey_ec, baserel);
+	if (em_expr == NULL)
+		return false;
+
+	/*
+	 * Finally, determine if it's safe to evaluate the found expr on the
+	 * foreign server.
+	 */
+	return is_foreign_expr(root, baserel, em_expr);
+}
+
 /*
  * Convert type OID + typmod info into a type name we can ship to the remote
  * server.  Someplace else had better have verified that this type name is
@@ -3331,6 +3371,45 @@ deparseAggref(Aggref *node, deparse_expr_cxt *context)
 	appendStringInfoChar(buf, ')');
 }
 
+/*
+ * Append the ASC, DESC, USING <OPERATOR> and NULLS FIRST / NULLS LAST part
+ * of the ORDER BY clause
+ */
+static void
+appendOrderBySuffix(Oid sortop, Oid sortcoltype, bool nulls_first,
+					deparse_expr_cxt *context)
+{
+	StringInfo	buf = context->buf;
+	TypeCacheEntry *typentry;
+
+	typentry = lookup_type_cache(sortcoltype, TYPECACHE_LT_OPR | TYPECACHE_GT_OPR);
+
+	if (sortop == typentry->lt_opr)
+		appendStringInfoString(buf, " ASC");
+	else if (sortop == typentry->gt_opr)
+		appendStringInfoString(buf, " DESC");
+	else
+	{
+		HeapTuple	opertup;
+		Form_pg_operator operform;
+
+		appendStringInfoString(buf, " USING ");
+
+		/* Append operator name. */
+		opertup = SearchSysCache1(OPEROID, ObjectIdGetDatum(sortop));
+		if (!HeapTupleIsValid(opertup))
+			elog(ERROR, "cache lookup failed for operator %u", sortop);
+		operform = (Form_pg_operator) GETSTRUCT(opertup);
+		deparseOperatorName(buf, operform);
+		ReleaseSysCache(opertup);
+	}
+
+	if (nulls_first)
+		appendStringInfoString(buf, " NULLS FIRST");
+	else
+		appendStringInfoString(buf, " NULLS LAST");
+}
+
 /*
  * Append ORDER BY within aggregate function.
  */
@@ -3346,7 +3425,6 @@ appendAggOrderBy(List *orderList, List *targetList, deparse_expr_cxt *context)
 		SortGroupClause *srt = (SortGroupClause *) lfirst(lc);
 		Node	   *sortexpr;
 		Oid			sortcoltype;
-		TypeCacheEntry *typentry;
 
 		if (!first)
 			appendStringInfoString(buf, ", ");
@@ -3356,32 +3434,8 @@ appendAggOrderBy(List *orderList, List *targetList, deparse_expr_cxt *context)
 										  false, context);
 		sortcoltype = exprType(sortexpr);
 		/* See whether operator is default < or > for datatype */
-		typentry = lookup_type_cache(sortcoltype,
-									 TYPECACHE_LT_OPR | TYPECACHE_GT_OPR);
-		if (srt->sortop == typentry->lt_opr)
-			appendStringInfoString(buf, " ASC");
-		else if (srt->sortop == typentry->gt_opr)
-			appendStringInfoString(buf, " DESC");
-		else
-		{
-			HeapTuple	opertup;
-			Form_pg_operator operform;
-
-			appendStringInfoString(buf, " USING ");
-
-			/* Append operator name. */
-			opertup = SearchSysCache1(OPEROID, ObjectIdGetDatum(srt->sortop));
-			if (!HeapTupleIsValid(opertup))
-				elog(ERROR, "cache lookup failed for operator %u", srt->sortop);
-			operform = (Form_pg_operator) GETSTRUCT(opertup);
-			deparseOperatorName(buf, operform);
-			ReleaseSysCache(opertup);
-		}
-
-		if (srt->nulls_first)
-			appendStringInfoString(buf, " NULLS FIRST");
-		else
-			appendStringInfoString(buf, " NULLS LAST");
+		appendOrderBySuffix(srt->sortop, sortcoltype, srt->nulls_first,
+							context);
 	}
 }
 
@@ -3486,7 +3540,11 @@ appendOrderByClause(List *pathkeys, bool has_final_sort,
 	foreach(lcell, pathkeys)
 	{
 		PathKey    *pathkey = lfirst(lcell);
+		EquivalenceMember *em;
 		Expr	   *em_expr;
+		HeapTuple	tuple;
+		Oid			oprid;
+		bool		isNull;
 
 		if (has_final_sort)
 		{
@@ -3494,26 +3552,44 @@ appendOrderByClause(List *pathkeys, bool has_final_sort,
 			 * By construction, context->foreignrel is the input relation to
 			 * the final sort.
 			 */
-			em_expr = find_em_expr_for_input_target(context->root,
-													pathkey->pk_eclass,
-													context->foreignrel->reltarget);
+			em = find_em_for_input_target(context->root,
+										  pathkey->pk_eclass,
+										  context->foreignrel->reltarget);
 		}
 		else
-			em_expr = find_em_expr_for_rel(pathkey->pk_eclass, baserel);
+			em = find_em_for_rel(pathkey->pk_eclass, baserel);
+
+		em_expr = em->em_expr;
+
+		/*
+		 * Lookup the operator corresponding to the strategy in the opclass.
+		 * The datatype used by the opfamily is not necessarily the same as
+		 * the expression type (for array types for example).
+		 */
+		tuple = SearchSysCache4(AMOPSTRATEGY,
+								ObjectIdGetDatum(pathkey->pk_opfamily),
+								ObjectIdGetDatum(em->em_datatype),
+								ObjectIdGetDatum(em->em_datatype),
+								Int16GetDatum(pathkey->pk_strategy));
+
+		if (!HeapTupleIsValid(tuple))
+			elog(ERROR, "missing operator %d(%u,%u) in opfamily %u",
+				 pathkey->pk_strategy, em->em_datatype, em->em_datatype,
+				 pathkey->pk_opfamily);
 
-		Assert(em_expr != NULL);
+		oprid = DatumGetObjectId(SysCacheGetAttr(AMOPSTRATEGY, tuple,
+												 Anum_pg_amop_amopopr, &isNull));
+		ReleaseSysCache(tuple);
 
 		appendStringInfoString(buf, delim);
 		deparseExpr(em_expr, context);
-		if (pathkey->pk_strategy == BTLessStrategyNumber)
-			appendStringInfoString(buf, " ASC");
-		else
-			appendStringInfoString(buf, " DESC");
 
-		if (pathkey->pk_nulls_first)
-			appendStringInfoString(buf, " NULLS FIRST");
-		else
-			appendStringInfoString(buf, " NULLS LAST");
+		/*
+		 * Here we need to use the expression type to compare against the
+		 * default btree sort operator.
+		 */
+		appendOrderBySuffix(oprid, exprType((Node *) em_expr),
+							pathkey->pk_nulls_first, context);
 
 		delim = ", ";
 	}
diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out
index e3ee30f1aa..1f44c365ef 100644
--- a/contrib/postgres_fdw/expected/postgres_fdw.out
+++ b/contrib/postgres_fdw/expected/postgres_fdw.out
@@ -3258,6 +3258,19 @@ select array_agg(c1 order by c1 using operator(public.<^)) from ft2 where c2 = 6
          Remote SQL: SELECT "C 1", c2 FROM "S 1"."T 1" WHERE (("C 1" < 100)) AND ((c2 = 6))
 (6 rows)
 
+-- Ensure that we don't push down an ORDER BY with a non-shippable operator
+explain (verbose, costs off)
+select * from ft2 order by c1 using operator(public.<^);
+                                  QUERY PLAN                                   
+-------------------------------------------------------------------------------
+ Sort
+   Output: c1, c2, c3, c4, c5, c6, c7, c8
+   Sort Key: ft2.c1 USING <^
+   ->  Foreign Scan on public.ft2
+         Output: c1, c2, c3, c4, c5, c6, c7, c8
+         Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1"
+(6 rows)
+
 -- Update local stats on ft2
 ANALYZE ft2;
 -- Add into extension
@@ -3285,6 +3298,16 @@ select array_agg(c1 order by c1 using operator(public.<^)) from ft2 where c2 = 6
  {6,16,26,36,46,56,66,76,86,96}
 (1 row)
 
+-- Ensure that the ORDER BY is pushed to the foreign server
+explain (verbose, costs off)
+select * from ft2 order by c1 using operator(public.<^);
+                                                         QUERY PLAN                                                          
+-----------------------------------------------------------------------------------------------------------------------------
+ Foreign Scan on public.ft2
+   Output: c1, c2, c3, c4, c5, c6, c7, c8
+   Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1" ORDER BY "C 1" USING OPERATOR(public.<^) NULLS LAST
+(3 rows)
+
 -- Remove from extension
 alter extension postgres_fdw drop operator class my_op_class using btree;
 alter extension postgres_fdw drop function my_op_cmp(a int, b int);
diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c
index 4bdab30a73..1dd4779185 100644
--- a/contrib/postgres_fdw/postgres_fdw.c
+++ b/contrib/postgres_fdw/postgres_fdw.c
@@ -917,8 +917,6 @@ get_useful_pathkeys_for_relation(PlannerInfo *root, RelOptInfo *rel)
 		foreach(lc, root->query_pathkeys)
 		{
 			PathKey    *pathkey = (PathKey *) lfirst(lc);
-			EquivalenceClass *pathkey_ec = pathkey->pk_eclass;
-			Expr	   *em_expr;
 
 			/*
 			 * The planner and executor don't have any clever strategy for
@@ -926,13 +924,8 @@ get_useful_pathkeys_for_relation(PlannerInfo *root, RelOptInfo *rel)
 			 * getting it to be sorted by all of those pathkeys. We'll just
 			 * end up resorting the entire data set.  So, unless we can push
 			 * down all of the query pathkeys, forget it.
-			 *
-			 * is_foreign_expr would detect volatile expressions as well, but
-			 * checking ec_has_volatile here saves some cycles.
 			 */
-			if (pathkey_ec->ec_has_volatile ||
-				!(em_expr = find_em_expr_for_rel(pathkey_ec, rel)) ||
-				!is_foreign_expr(root, rel, em_expr))
+			if (!is_foreign_pathkey(root, rel, pathkey))
 			{
 				query_pathkeys_ok = false;
 				break;
@@ -6540,9 +6533,9 @@ add_foreign_ordered_paths(PlannerInfo *root, RelOptInfo *input_rel,
 			return;
 
 		/* Get the sort expression for the pathkey_ec */
-		sort_expr = find_em_expr_for_input_target(root,
-												  pathkey_ec,
-												  input_rel->reltarget);
+		sort_expr = find_em_for_input_target(root,
+											 pathkey_ec,
+											 input_rel->reltarget)->em_expr;
 
 		/* If it's unsafe to remote, we cannot push down the final sort */
 		if (!is_foreign_expr(root, input_rel, sort_expr))
@@ -7332,13 +7325,12 @@ conversion_error_callback(void *arg)
 }
 
 /*
- * Find an equivalence class member expression to be computed as a sort column
- * in the given target.
+ * Find an equivalence class member to be computed as a sort column in the
+ * given target.
  */
-Expr *
-find_em_expr_for_input_target(PlannerInfo *root,
-							  EquivalenceClass *ec,
-							  PathTarget *target)
+EquivalenceMember *
+find_em_for_input_target(PlannerInfo *root, EquivalenceClass *ec,
+						 PathTarget *target)
 {
 	ListCell   *lc1;
 	int			i;
@@ -7383,7 +7375,7 @@ find_em_expr_for_input_target(PlannerInfo *root,
 				em_expr = ((RelabelType *) em_expr)->arg;
 
 			if (equal(em_expr, expr))
-				return em->em_expr;
+				return em;
 		}
 
 		i++;
diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h
index ca83306af9..9930226b6f 100644
--- a/contrib/postgres_fdw/postgres_fdw.h
+++ b/contrib/postgres_fdw/postgres_fdw.h
@@ -171,6 +171,9 @@ extern bool is_foreign_expr(PlannerInfo *root,
 extern bool is_foreign_param(PlannerInfo *root,
 							 RelOptInfo *baserel,
 							 Expr *expr);
+extern bool is_foreign_pathkey(PlannerInfo *root,
+							   RelOptInfo *baserel,
+							   PathKey *pathkey);
 extern void deparseInsertSql(StringInfo buf, RangeTblEntry *rte,
 							 Index rtindex, Relation rel,
 							 List *targetAttrs, bool doNothing,
@@ -213,10 +216,10 @@ extern void deparseTruncateSql(StringInfo buf,
 							   DropBehavior behavior,
 							   bool restart_seqs);
 extern void deparseStringLiteral(StringInfo buf, const char *val);
-extern Expr *find_em_expr_for_rel(EquivalenceClass *ec, RelOptInfo *rel);
-extern Expr *find_em_expr_for_input_target(PlannerInfo *root,
-										   EquivalenceClass *ec,
-										   PathTarget *target);
+extern EquivalenceMember *find_em_for_rel(EquivalenceClass *ec, RelOptInfo *rel);
+extern EquivalenceMember *find_em_for_input_target(PlannerInfo *root,
+												   EquivalenceClass *ec,
+												   PathTarget *target);
 extern List *build_tlist_to_deparse(RelOptInfo *foreignrel);
 extern void deparseSelectStmtForRel(StringInfo buf, PlannerInfo *root,
 									RelOptInfo *foreignrel, List *tlist,
diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql
index 30b5175da5..1bbe1212c4 100644
--- a/contrib/postgres_fdw/sql/postgres_fdw.sql
+++ b/contrib/postgres_fdw/sql/postgres_fdw.sql
@@ -902,6 +902,10 @@ create operator class my_op_class for type int using btree family my_op_family a
 explain (verbose, costs off)
 select array_agg(c1 order by c1 using operator(public.<^)) from ft2 where c2 = 6 and c1 < 100 group by c2;
 
+-- Ensure that we don't push down an ORDER BY with a non-shippable operator
+explain (verbose, costs off)
+select * from ft2 order by c1 using operator(public.<^);
+
 -- Update local stats on ft2
 ANALYZE ft2;
 
@@ -919,6 +923,10 @@ explain (verbose, costs off)
 select array_agg(c1 order by c1 using operator(public.<^)) from ft2 where c2 = 6 and c1 < 100 group by c2;
 select array_agg(c1 order by c1 using operator(public.<^)) from ft2 where c2 = 6 and c1 < 100 group by c2;
 
+-- Ensure that the ORDER BY is pushed to the foreign server
+explain (verbose, costs off)
+select * from ft2 order by c1 using operator(public.<^);
+
 -- Remove from extension
 alter extension postgres_fdw drop operator class my_op_class using btree;
 alter extension postgres_fdw drop function my_op_cmp(a int, b int);
diff --git a/src/backend/optimizer/path/equivclass.c b/src/backend/optimizer/path/equivclass.c
index 6f1abbe47d..b367f18eab 100644
--- a/src/backend/optimizer/path/equivclass.c
+++ b/src/backend/optimizer/path/equivclass.c
@@ -932,11 +932,11 @@ is_exprlist_member(Expr *node, List *exprs)
 }
 
 /*
- * Find an equivalence class member expression, all of whose Vars, come from
- * the indicated relation.
+ * Find an equivalence class member, all of whose Vars, come from the
+ * indicated relation.
  */
-Expr *
-find_em_expr_for_rel(EquivalenceClass *ec, RelOptInfo *rel)
+EquivalenceMember *
+find_em_for_rel(EquivalenceClass *ec, RelOptInfo *rel)
 {
 	ListCell   *lc_em;
 
@@ -952,7 +952,7 @@ find_em_expr_for_rel(EquivalenceClass *ec, RelOptInfo *rel)
 			 * taken entirely from this relation, we'll be content to choose
 			 * any one of those.
 			 */
-			return em->em_expr;
+			return em;
 		}
 	}
 
@@ -960,6 +960,22 @@ find_em_expr_for_rel(EquivalenceClass *ec, RelOptInfo *rel)
 	return NULL;
 }
 
+/*
+ * Find an equivalence class member expression, all of whose Vars, come from
+ * the indicated relation.
+ */
+Expr *
+find_em_expr_for_rel(EquivalenceClass *ec, RelOptInfo *rel)
+{
+	EquivalenceMember *em = find_em_for_rel(ec, rel);
+
+	if (em != NULL)
+		return em->em_expr;
+
+	return NULL;
+}
+
+
 /*
  * relation_can_be_sorted_early
  *		Can this relation be sorted on this EC before the final output step?
diff --git a/src/include/optimizer/paths.h b/src/include/optimizer/paths.h
index f1d111063c..5a2bbc87e1 100644
--- a/src/include/optimizer/paths.h
+++ b/src/include/optimizer/paths.h
@@ -144,6 +144,8 @@ extern EquivalenceMember *find_computable_ec_member(PlannerInfo *root,
 													Relids relids,
 													bool require_parallel_safe);
 extern Expr *find_em_expr_for_rel(EquivalenceClass *ec, RelOptInfo *rel);
+extern EquivalenceMember *find_em_for_rel(EquivalenceClass *ec,
+										  RelOptInfo *rel);
 extern bool relation_can_be_sorted_early(PlannerInfo *root, RelOptInfo *rel,
 										 EquivalenceClass *ec,
 										 bool require_parallel_safe);
-- 
2.33.0


--nextPart1657077.ZGz24vUy9i--








^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v1 1/5] Allow to use multiple shared memory mappings
@ 2024-10-09 13:41  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2024-10-09 13:41 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory slot.
There is only fixed amount of available slots, currently only one main
shared memory slot is allocated. A new shared memory API is introduces,
extended with a slot as a new parameter. As a path of least resistance,
the original API is kept in place, utilizing the main shared memory slot.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   2 +-
 src/backend/storage/ipc/ipci.c      |  61 ++++++------
 src/backend/storage/ipc/shmem.c     | 133 ++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  10 ++
 13 files changed, 258 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 64186ec0a7..b97723d2ed 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 5b88a92bc9..8ef95b12c9 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSlot(PGSemaphoreShmemSize(maxSemas), shmem_slot);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 362a37d3b3..065a5b63ac 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_slot;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping slots */
+static int next_free_slot = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_slot)
+{
+	switch (shmem_slot)
+	{
+		case MAIN_SHMEM_SLOT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_slot; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "slot[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_slot), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("slot[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_slot)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_slot];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_slot = next_free_slot;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_slot++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_slot;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_slot; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index f2b54bdfda..d62084cc0d 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_slot)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index b06e4b8452..2aabd4a77f 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -68,7 +68,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 35fa2e1dda..8224015b53 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -88,7 +88,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_slot)
 {
 	Size		size;
 	int			numSemas;
@@ -202,33 +202,36 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int slot = 0; slot < ANON_MAPPINGS; slot++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, slot);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSlot(seghdr, slot);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, slot);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSlot(slot);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -359,7 +362,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SLOT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 6d5f083986..c670b9cf43 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,17 +75,12 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSlot(Size size, Size *allocated_size,
+								 int shmem_slot);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
-
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
+ShmemSegment Segments[ANON_MAPPINGS];
 
 static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 
@@ -99,11 +94,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(void *seghdr)
 {
-	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	InitShmemAccessInSlot(seghdr, MAIN_SHMEM_SLOT);
+}
 
-	ShmemSegHdr = shmhdr;
-	ShmemBase = (void *) shmhdr;
-	ShmemEnd = (char *) ShmemBase + shmhdr->totalsize;
+void
+InitShmemAccessInSlot(void *seghdr, int shmem_slot)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_slot];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +115,13 @@ InitShmemAccess(void *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSlot(MAIN_SHMEM_SLOT);
+}
+
+void
+InitShmemAllocationInSlot(int shmem_slot)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_slot].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +130,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_slot].ShmemLock = (slock_t *) ShmemAllocUnlockedInSlot(sizeof(slock_t), shmem_slot);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_slot].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +157,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocInSlot(Size size, int shmem_slot)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +197,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSlot(size, allocated_size, MAIN_SHMEM_SLOT);
+}
+
+static void *
+ShmemAllocRawInSlot(Size size, Size *allocated_size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +222,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_slot].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_slot].ShmemSegHdr->totalsize)
 	{
-		newSpace = (void *) ((char *) ShmemBase + newStart);
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
+		Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_slot].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +255,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSlot(size, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemAllocUnlockedInSlot(Size size, int shmem_slot)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +271,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_slot].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_slot].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_slot].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_slot].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (void *) ((char *) ShmemBase + newStart);
+	newSpace = (void *) ((char *) Segments[shmem_slot].ShmemBase + newStart);
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +298,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSlot(addr, MAIN_SHMEM_SLOT);
+}
+
+bool
+ShmemAddrIsValidInSlot(const void *addr, int shmem_slot)
+{
+	return (addr >= Segments[shmem_slot].ShmemBase) && (addr < Segments[shmem_slot].ShmemEnd);
 }
 
 /*
@@ -334,6 +365,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSlot(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SLOT);
+}
+
+HTAB *
+ShmemInitHashInSlot(const char *name,		/* table string name for shmem index */
+			  long init_size,	/* initial table size */
+			  long max_size,	/* max size of the table */
+			  HASHCTL *infoP,	/* info about key and bucket size */
+			  int hash_flags,	/* info about infoP */
+			  int shmem_slot) 	/* in which slot to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +393,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSlot(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_slot);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +428,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSlot(name, size, foundPtr, MAIN_SHMEM_SLOT);
+}
+
+void *
+ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+					  int shmem_slot)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +443,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_slot].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +466,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSlot(size, shmem_slot);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +483,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in slot %d",
+						name, shmem_slot)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +509,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSlot(size, &allocated_size, shmem_slot);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +528,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSlot(structPtr, shmem_slot));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -545,7 +594,7 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SLOT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +606,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SLOT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index e765754d80..fb0c33bf17 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SLOT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index f190e6e5e4..aef80e049b 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -23,6 +23,7 @@
 #include "storage/latch.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index b2d062781e..be4b131288 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_slot);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index dfef79ac96..081fffaf16 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_slot);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 3065ff5be7..e968deeef7 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+// Number of available slots for anonymous memory mappings
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main slot, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SLOT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 842989111c..d3e9cc721d 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -28,15 +28,25 @@
 /* shmem.c */
 extern PGDLLIMPORT slock_t *ShmemLock;
 extern void InitShmemAccess(void *seghdr);
+extern void InitShmemAccessInSlot(void *seghdr, int shmem_slot);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSlot(int shmem_slot);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSlot(Size size, int shmem_slot);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSlot(Size size, int shmem_slot);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSlot(const void *addr, int shmem_slot);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSlot(const char *name, long init_size, long max_size,
+						   HASHCTL *infoP, int hash_flags, int shmem_slot);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSlot(const char *name, Size size, bool *foundPtr,
+								   int shmem_slot);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 2488058dc356a43455b21a099ea879fff9266634
-- 
2.45.1


--ers4zrhjqnhlajas
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v1-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v2 1/6] Allow to use multiple shared memory mappings
@ 2025-02-19 16:43  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-19 16:43 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c       |   4 +-
 src/backend/port/sysv_sema.c        |   4 +-
 src/backend/port/sysv_shmem.c       | 138 ++++++++++++++++++---------
 src/backend/port/win32_sema.c       |   2 +-
 src/backend/storage/ipc/ipc.c       |   4 +-
 src/backend/storage/ipc/ipci.c      |  63 +++++++------
 src/backend/storage/ipc/shmem.c     | 141 +++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c   |   5 +-
 src/include/storage/buf_internals.h |   1 +
 src/include/storage/ipc.h           |   2 +-
 src/include/storage/pg_sema.h       |   2 +-
 src/include/storage/pg_shmem.h      |  18 ++++
 src/include/storage/shmem.h         |  12 +++
 13 files changed, 272 insertions(+), 124 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..843b1b3220f 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	void *shmem; 				/* Pointer to the start of the mapped memory */
+	void *seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index e4d5b944e12..9d526eb43fd 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 174eed70367..4f6c707c204 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -85,7 +85,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -204,33 +204,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -360,7 +365,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index f1e74f184f1..40aa4014b5f 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -81,6 +81,7 @@
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
 #include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/spin.h"
@@ -607,9 +608,9 @@ LWLockNewTrancheId(void)
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
 	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 1a65342177d..4595f5a9676 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -22,6 +22,7 @@
 #include "storage/condition_variable.h"
 #include "storage/lwlock.h"
 #include "storage/shmem.h"
+#include "storage/pg_shmem.h"
 #include "storage/smgr.h"
 #include "storage/spin.h"
 #include "utils/relcache.h"
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index e0f5f92e947..c0439f2206b 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 80d7f990496b1c7be61d9a00a2635b7d96b96197
-- 
2.45.1


--q7xzg7duksj2kgko
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v2-0002-Allow-placing-shared-memory-mapping-with-an-offse.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v4 1/8] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 ++++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 141 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 278 insertions(+), 125 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index f7c8638aec5..b6301463ac7 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -313,7 +313,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -334,7 +334,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index 895a43fb39e..389abc82519 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -75,19 +75,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 
 /*
@@ -96,9 +96,17 @@ static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -109,7 +117,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -118,9 +132,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -145,11 +159,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -179,6 +199,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -198,22 +224,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -231,6 +257,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -241,19 +273,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -268,7 +300,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -329,6 +367,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -345,9 +395,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -380,6 +430,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -388,7 +445,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -411,7 +468,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -428,8 +485,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -454,7 +511,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -473,14 +530,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -537,10 +593,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -552,15 +609,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 3df29658f18..8241c061507 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index b99ebc9e86f..138078c29c5 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -90,4 +105,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index 904a336b851..5929f140236 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 

base-commit: 5e1915439085014140314979c4dd5e23bd677cac
-- 
2.45.1


--vninua6xybvzgrci
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v4-0002-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread

* [PATCH v5 04/10] Allow to use multiple shared memory mappings
@ 2025-02-28 18:54  Dmitrii Dolgov <[email protected]>
  0 siblings, 0 replies; 309+ messages in thread

From: Dmitrii Dolgov @ 2025-02-28 18:54 UTC (permalink / raw)

Currently all the work with shared memory is done via a single anonymous
memory mapping, which limits ways how the shared memory could be organized.

Introduce possibility to allocate multiple shared memory mappings, where
a single mapping is associated with a specified shared memory segment.
There is only fixed amount of available segments, currently only one
main shared memory segment is allocated. A new shared memory API is
introduces, extended with a segment as a new parameter. As a path of
least resistance, the original API is kept in place, utilizing the main
shared memory segment.
---
 src/backend/port/posix_sema.c     |   4 +-
 src/backend/port/sysv_sema.c      |   4 +-
 src/backend/port/sysv_shmem.c     | 138 +++++++++++++++++++---------
 src/backend/port/win32_sema.c     |   2 +-
 src/backend/storage/ipc/ipc.c     |   4 +-
 src/backend/storage/ipc/ipci.c    |  63 +++++++------
 src/backend/storage/ipc/shmem.c   | 148 +++++++++++++++++++++---------
 src/backend/storage/lmgr/lwlock.c |  13 ++-
 src/include/storage/ipc.h         |   2 +-
 src/include/storage/pg_sema.h     |   2 +-
 src/include/storage/pg_shmem.h    |  18 ++++
 src/include/storage/shmem.h       |  12 +++
 12 files changed, 284 insertions(+), 126 deletions(-)

diff --git a/src/backend/port/posix_sema.c b/src/backend/port/posix_sema.c
index 269c7460817..401e1113fa1 100644
--- a/src/backend/port/posix_sema.c
+++ b/src/backend/port/posix_sema.c
@@ -193,7 +193,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * we don't have to expose the counters to other processes.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -220,7 +220,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 #endif
 
 	numSems = 0;
diff --git a/src/backend/port/sysv_sema.c b/src/backend/port/sysv_sema.c
index 423b2b4f9d6..4ce2cfb662b 100644
--- a/src/backend/port/sysv_sema.c
+++ b/src/backend/port/sysv_sema.c
@@ -307,7 +307,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * have clobbered.)
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	struct stat statbuf;
 
@@ -328,7 +328,7 @@ PGReserveSemaphores(int maxSemas)
 	 * ShmemAlloc() won't be ready yet.
 	 */
 	sharedSemas = (PGSemaphore)
-		ShmemAllocUnlocked(PGSemaphoreShmemSize(maxSemas));
+		ShmemAllocUnlockedInSegment(PGSemaphoreShmemSize(maxSemas), shmem_segment);
 	numSharedSemas = 0;
 	maxSharedSemas = maxSemas;
 
diff --git a/src/backend/port/sysv_shmem.c b/src/backend/port/sysv_shmem.c
index 197926d44f6..56af0231d24 100644
--- a/src/backend/port/sysv_shmem.c
+++ b/src/backend/port/sysv_shmem.c
@@ -94,8 +94,19 @@ typedef enum
 unsigned long UsedShmemSegID = 0;
 void	   *UsedShmemSegAddr = NULL;
 
-static Size AnonymousShmemSize;
-static void *AnonymousShmem = NULL;
+typedef struct AnonymousMapping
+{
+	int shmem_segment;
+	Size shmem_size; 			/* Size of the mapping */
+	Pointer shmem; 				/* Pointer to the start of the mapped memory */
+	Pointer seg_addr; 			/* SysV shared memory for the header */
+	unsigned long seg_id; 		/* IPC key */
+} AnonymousMapping;
+
+static AnonymousMapping Mappings[ANON_MAPPINGS];
+
+/* Keeps track of used mapping segments */
+static int next_free_segment = 0;
 
 static void *InternalIpcMemoryCreate(IpcMemoryKey memKey, Size size);
 static void IpcMemoryDetach(int status, Datum shmaddr);
@@ -104,6 +115,28 @@ static IpcMemoryState PGSharedMemoryAttach(IpcMemoryId shmId,
 										   void *attachAt,
 										   PGShmemHeader **addr);
 
+static const char*
+MappingName(int shmem_segment)
+{
+	switch (shmem_segment)
+	{
+		case MAIN_SHMEM_SEGMENT:
+			return "main";
+		default:
+			return "unknown";
+	}
+}
+
+static void
+DebugMappings()
+{
+	for(int i = 0; i < next_free_segment; i++)
+	{
+		AnonymousMapping m = Mappings[i];
+		elog(DEBUG1, "Mapping[%s]: addr %p, size %zu",
+			 MappingName(i), m.shmem, m.shmem_size);
+	}
+}
 
 /*
  *	InternalIpcMemoryCreate(memKey, size)
@@ -591,14 +624,13 @@ check_huge_page_size(int *newval, void **extra, GucSource source)
 /*
  * Creates an anonymous mmap()ed shared memory segment.
  *
- * Pass the requested size in *size.  This function will modify *size to the
- * actual size of the allocation, if it ends up allocating a segment that is
- * larger than requested.
+ * This function will modify mapping size to the actual size of the allocation,
+ * if it ends up allocating a segment that is larger than requested.
  */
-static void *
-CreateAnonymousSegment(Size *size)
+static void
+CreateAnonymousSegment(AnonymousMapping *mapping)
 {
-	Size		allocsize = *size;
+	Size		allocsize = mapping->shmem_size;
 	void	   *ptr = MAP_FAILED;
 	int			mmap_errno = 0;
 
@@ -623,8 +655,11 @@ CreateAnonymousSegment(Size *size)
 				   PG_MMAP_FLAGS | mmap_flags, -1, 0);
 		mmap_errno = errno;
 		if (huge_pages == HUGE_PAGES_TRY && ptr == MAP_FAILED)
-			elog(DEBUG1, "mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
-				 allocsize);
+		{
+			DebugMappings();
+			elog(DEBUG1, "segment[%s]: mmap(%zu) with MAP_HUGETLB failed, huge pages disabled: %m",
+				 MappingName(mapping->shmem_segment), allocsize);
+		}
 	}
 #endif
 
@@ -642,7 +677,7 @@ CreateAnonymousSegment(Size *size)
 		 * Use the original size, not the rounded-up value, when falling back
 		 * to non-huge pages.
 		 */
-		allocsize = *size;
+		allocsize = mapping->shmem_size;
 		ptr = mmap(NULL, allocsize, PROT_READ | PROT_WRITE,
 				   PG_MMAP_FLAGS, -1, 0);
 		mmap_errno = errno;
@@ -651,8 +686,10 @@ CreateAnonymousSegment(Size *size)
 	if (ptr == MAP_FAILED)
 	{
 		errno = mmap_errno;
+		DebugMappings();
 		ereport(FATAL,
-				(errmsg("could not map anonymous shared memory: %m"),
+				(errmsg("segment[%s]: could not map anonymous shared memory: %m",
+						MappingName(mapping->shmem_segment)),
 				 (mmap_errno == ENOMEM) ?
 				 errhint("This error usually means that PostgreSQL's request "
 						 "for a shared memory segment exceeded available memory, "
@@ -663,8 +700,8 @@ CreateAnonymousSegment(Size *size)
 						 allocsize) : 0));
 	}
 
-	*size = allocsize;
-	return ptr;
+	mapping->shmem = ptr;
+	mapping->shmem_size = allocsize;
 }
 
 /*
@@ -674,13 +711,18 @@ CreateAnonymousSegment(Size *size)
 static void
 AnonymousShmemDetach(int status, Datum arg)
 {
-	/* Release anonymous shared memory block, if any. */
-	if (AnonymousShmem != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		AnonymousMapping m = Mappings[i];
+
+		/* Release anonymous shared memory block, if any. */
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
 
@@ -705,6 +747,7 @@ PGSharedMemoryCreate(Size size,
 	PGShmemHeader *hdr;
 	struct stat statbuf;
 	Size		sysvsize;
+	AnonymousMapping *mapping = &Mappings[next_free_segment];
 
 	/*
 	 * We use the data directory's ID info (inode and device numbers) to
@@ -733,11 +776,15 @@ PGSharedMemoryCreate(Size size,
 
 	/* Room for a header? */
 	Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
+	mapping->shmem_size = size;
+	mapping->shmem_segment = next_free_segment;
 
 	if (shared_memory_type == SHMEM_TYPE_MMAP)
 	{
-		AnonymousShmem = CreateAnonymousSegment(&size);
-		AnonymousShmemSize = size;
+		/* On success, mapping data will be modified. */
+		CreateAnonymousSegment(mapping);
+
+		next_free_segment++;
 
 		/* Register on-exit routine to unmap the anonymous segment */
 		on_shmem_exit(AnonymousShmemDetach, (Datum) 0);
@@ -760,7 +807,7 @@ PGSharedMemoryCreate(Size size,
 	 * loop simultaneously.  (CreateDataDirLockFile() does not entirely ensure
 	 * that, but prefer fixing it over coping here.)
 	 */
-	NextShmemSegID = statbuf.st_ino;
+	NextShmemSegID = statbuf.st_ino + next_free_segment;
 
 	for (;;)
 	{
@@ -852,13 +899,13 @@ PGSharedMemoryCreate(Size size,
 	/*
 	 * Initialize space allocation status for segment.
 	 */
-	hdr->totalsize = size;
+	hdr->totalsize = mapping->shmem_size;
 	hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
 	*shim = hdr;
 
 	/* Save info for possible future use */
-	UsedShmemSegAddr = memAddress;
-	UsedShmemSegID = (unsigned long) NextShmemSegID;
+	mapping->seg_addr = memAddress;
+	mapping->seg_id = (unsigned long) NextShmemSegID;
 
 	/*
 	 * If AnonymousShmem is NULL here, then we're not using anonymous shared
@@ -866,10 +913,10 @@ PGSharedMemoryCreate(Size size,
 	 * block. Otherwise, the System V shared memory block is only a shim, and
 	 * we must return a pointer to the real block.
 	 */
-	if (AnonymousShmem == NULL)
+	if (mapping->shmem == NULL)
 		return hdr;
-	memcpy(AnonymousShmem, hdr, sizeof(PGShmemHeader));
-	return (PGShmemHeader *) AnonymousShmem;
+	memcpy(mapping->shmem, hdr, sizeof(PGShmemHeader));
+	return (PGShmemHeader *) mapping->shmem;
 }
 
 #ifdef EXEC_BACKEND
@@ -969,23 +1016,28 @@ PGSharedMemoryNoReAttach(void)
 void
 PGSharedMemoryDetach(void)
 {
-	if (UsedShmemSegAddr != NULL)
+	for(int i = 0; i < next_free_segment; i++)
 	{
-		if ((shmdt(UsedShmemSegAddr) < 0)
+		AnonymousMapping m = Mappings[i];
+
+		if (m.seg_addr != NULL)
+		{
+			if ((shmdt(m.seg_addr) < 0)
 #if defined(EXEC_BACKEND) && defined(__CYGWIN__)
-		/* Work-around for cygipc exec bug */
-			&& shmdt(NULL) < 0
+			/* Work-around for cygipc exec bug */
+				&& shmdt(NULL) < 0
 #endif
-			)
-			elog(LOG, "shmdt(%p) failed: %m", UsedShmemSegAddr);
-		UsedShmemSegAddr = NULL;
-	}
+				)
+				elog(LOG, "shmdt(%p) failed: %m", m.seg_addr);
+			m.seg_addr = NULL;
+		}
 
-	if (AnonymousShmem != NULL)
-	{
-		if (munmap(AnonymousShmem, AnonymousShmemSize) < 0)
-			elog(LOG, "munmap(%p, %zu) failed: %m",
-				 AnonymousShmem, AnonymousShmemSize);
-		AnonymousShmem = NULL;
+		if (m.shmem != NULL)
+		{
+			if (munmap(m.shmem, m.shmem_size) < 0)
+				elog(LOG, "munmap(%p, %zu) failed: %m",
+					 m.shmem, m.shmem_size);
+			m.shmem = NULL;
+		}
 	}
 }
diff --git a/src/backend/port/win32_sema.c b/src/backend/port/win32_sema.c
index 5854ad1f54d..e7365ff8060 100644
--- a/src/backend/port/win32_sema.c
+++ b/src/backend/port/win32_sema.c
@@ -44,7 +44,7 @@ PGSemaphoreShmemSize(int maxSemas)
  * process exits.
  */
 void
-PGReserveSemaphores(int maxSemas)
+PGReserveSemaphores(int maxSemas, int shmem_segment)
 {
 	mySemSet = (HANDLE *) malloc(maxSemas * sizeof(HANDLE));
 	if (mySemSet == NULL)
diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index 567739b5be9..5b55bec8d9d 100644
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -61,6 +61,8 @@ static void proc_exit_prepare(int code);
  * but provide some additional features we need --- in particular,
  * we want to register callbacks to invoke when we are disconnecting
  * from a broken shared-memory context but not exiting the postmaster.
+ * Maximum number of such exit callbacks depends on the number of shared
+ * segments.
  *
  * Callback functions can take zero, one, or two args: the first passed
  * arg is the integer exitcode, the second is the Datum supplied when
@@ -68,7 +70,7 @@ static void proc_exit_prepare(int code);
  * ----------------------------------------------------------------
  */
 
-#define MAX_ON_EXITS 20
+#define MAX_ON_EXITS 40
 
 struct ONEXIT
 {
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index 2fa045e6b0f..8b38e985327 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -86,7 +86,7 @@ RequestAddinShmemSpace(Size size)
  * required.
  */
 Size
-CalculateShmemSize(int *num_semaphores)
+CalculateShmemSize(int *num_semaphores, int shmem_segment)
 {
 	Size		size;
 	int			numSemas;
@@ -206,33 +206,38 @@ CreateSharedMemoryAndSemaphores(void)
 
 	Assert(!IsUnderPostmaster);
 
-	/* Compute the size of the shared-memory block */
-	size = CalculateShmemSize(&numSemas);
-	elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
-
-	/*
-	 * Create the shmem segment
-	 */
-	seghdr = PGSharedMemoryCreate(size, &shim);
-
-	/*
-	 * Make sure that huge pages are never reported as "unknown" while the
-	 * server is running.
-	 */
-	Assert(strcmp("unknown",
-				  GetConfigOption("huge_pages_status", false, false)) != 0);
-
-	InitShmemAccess(seghdr);
-
-	/*
-	 * Create semaphores
-	 */
-	PGReserveSemaphores(numSemas);
-
-	/*
-	 * Set up shared memory allocation mechanism
-	 */
-	InitShmemAllocation();
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		/* Compute the size of the shared-memory block */
+		size = CalculateShmemSize(&numSemas, segment);
+		elog(DEBUG3, "invoking IpcMemoryCreate(size=%zu)", size);
+
+		/*
+		 * Create the shmem segment.
+		 *
+		 * XXX: Do multiple shims are needed, one per segment?
+		 */
+		seghdr = PGSharedMemoryCreate(size, &shim);
+
+		/*
+		 * Make sure that huge pages are never reported as "unknown" while the
+		 * server is running.
+		 */
+		Assert(strcmp("unknown",
+					  GetConfigOption("huge_pages_status", false, false)) != 0);
+
+		InitShmemAccessInSegment(seghdr, segment);
+
+		/*
+		 * Create semaphores
+		 */
+		PGReserveSemaphores(numSemas, segment);
+
+		/*
+		 * Set up shared memory allocation mechanism
+		 */
+		InitShmemAllocationInSegment(segment);
+	}
 
 	/* Initialize subsystems */
 	CreateOrAttachShmemStructs();
@@ -363,7 +368,7 @@ InitializeShmemGUCs(void)
 	/*
 	 * Calculate the shared memory size and round up to the nearest megabyte.
 	 */
-	size_b = CalculateShmemSize(&num_semas);
+	size_b = CalculateShmemSize(&num_semas, MAIN_SHMEM_SEGMENT);
 	size_mb = add_size(size_b, (1024 * 1024) - 1) / (1024 * 1024);
 	sprintf(buf, "%zu", size_mb);
 	SetConfigOption("shared_memory_size", buf,
diff --git a/src/backend/storage/ipc/shmem.c b/src/backend/storage/ipc/shmem.c
index c9ae3b45b76..72255a1c5ca 100644
--- a/src/backend/storage/ipc/shmem.c
+++ b/src/backend/storage/ipc/shmem.c
@@ -76,19 +76,19 @@
 #include "utils/builtins.h"
 
 static void *ShmemAllocRaw(Size size, Size *allocated_size);
+static void *ShmemAllocRawInSegment(Size size, Size *allocated_size,
+								 int shmem_segment);
 
 /* shared memory global variables */
 
-static PGShmemHeader *ShmemSegHdr;	/* shared mem segment header */
+ShmemSegment Segments[ANON_MAPPINGS];
 
-static void *ShmemBase;			/* start address of shared memory */
-
-static void *ShmemEnd;			/* end+1 address of shared memory */
-
-slock_t    *ShmemLock;			/* spinlock for shared memory and LWLock
-								 * allocation */
-
-static HTAB *ShmemIndex = NULL; /* primary index hashtable for shmem */
+/*
+ * Primary index hashtable for shmem, for simplicity we use a single for all
+ * shared memory segments. There can be performance consequences of that, and
+ * an alternative option would be to have one index per shared memory segments.
+ */
+static HTAB *ShmemIndex = NULL;
 
 /* To get reliable results for NUMA inquiry we need to "touch pages" once */
 static bool firstNumaTouch = true;
@@ -101,9 +101,17 @@ Datum		pg_numa_available(PG_FUNCTION_ARGS);
 void
 InitShmemAccess(PGShmemHeader *seghdr)
 {
-	ShmemSegHdr = seghdr;
-	ShmemBase = seghdr;
-	ShmemEnd = (char *) ShmemBase + seghdr->totalsize;
+	InitShmemAccessInSegment(seghdr, MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAccessInSegment(PGShmemHeader *seghdr, int shmem_segment)
+{
+	PGShmemHeader *shmhdr = (PGShmemHeader *) seghdr;
+	ShmemSegment *seg = &Segments[shmem_segment];
+	seg->ShmemSegHdr = shmhdr;
+	seg->ShmemBase = (void *) shmhdr;
+	seg->ShmemEnd = (char *) seg->ShmemBase + shmhdr->totalsize;
 }
 
 /*
@@ -114,7 +122,13 @@ InitShmemAccess(PGShmemHeader *seghdr)
 void
 InitShmemAllocation(void)
 {
-	PGShmemHeader *shmhdr = ShmemSegHdr;
+	InitShmemAllocationInSegment(MAIN_SHMEM_SEGMENT);
+}
+
+void
+InitShmemAllocationInSegment(int shmem_segment)
+{
+	PGShmemHeader *shmhdr = Segments[shmem_segment].ShmemSegHdr;
 	char	   *aligned;
 
 	Assert(shmhdr != NULL);
@@ -123,9 +137,9 @@ InitShmemAllocation(void)
 	 * Initialize the spinlock used by ShmemAlloc.  We must use
 	 * ShmemAllocUnlocked, since obviously ShmemAlloc can't be called yet.
 	 */
-	ShmemLock = (slock_t *) ShmemAllocUnlocked(sizeof(slock_t));
+	Segments[shmem_segment].ShmemLock = (slock_t *) ShmemAllocUnlockedInSegment(sizeof(slock_t), shmem_segment);
 
-	SpinLockInit(ShmemLock);
+	SpinLockInit(Segments[shmem_segment].ShmemLock);
 
 	/*
 	 * Allocations after this point should go through ShmemAlloc, which
@@ -150,11 +164,17 @@ InitShmemAllocation(void)
  */
 void *
 ShmemAlloc(Size size)
+{
+	return ShmemAllocInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocInSegment(Size size, int shmem_segment)
 {
 	void	   *newSpace;
 	Size		allocated_size;
 
-	newSpace = ShmemAllocRaw(size, &allocated_size);
+	newSpace = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 	if (!newSpace)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
@@ -184,6 +204,12 @@ ShmemAllocNoError(Size size)
  */
 static void *
 ShmemAllocRaw(Size size, Size *allocated_size)
+{
+	return ShmemAllocRawInSegment(size, allocated_size, MAIN_SHMEM_SEGMENT);
+}
+
+static void *
+ShmemAllocRawInSegment(Size size, Size *allocated_size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -203,22 +229,22 @@ ShmemAllocRaw(Size size, Size *allocated_size)
 	size = CACHELINEALIGN(size);
 	*allocated_size = size;
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	SpinLockAcquire(ShmemLock);
+	SpinLockAcquire(Segments[shmem_segment].ShmemLock);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree <= ShmemSegHdr->totalsize)
+	if (newFree <= Segments[shmem_segment].ShmemSegHdr->totalsize)
 	{
-		newSpace = (char *) ShmemBase + newStart;
-		ShmemSegHdr->freeoffset = newFree;
+		newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
+		Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 	}
 	else
 		newSpace = NULL;
 
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[shmem_segment].ShmemLock);
 
 	/* note this assert is okay with newSpace == NULL */
 	Assert(newSpace == (void *) CACHELINEALIGN(newSpace));
@@ -236,6 +262,12 @@ ShmemAllocRaw(Size size, Size *allocated_size)
  */
 void *
 ShmemAllocUnlocked(Size size)
+{
+	return ShmemAllocUnlockedInSegment(size, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemAllocUnlockedInSegment(Size size, int shmem_segment)
 {
 	Size		newStart;
 	Size		newFree;
@@ -246,19 +278,19 @@ ShmemAllocUnlocked(Size size)
 	 */
 	size = MAXALIGN(size);
 
-	Assert(ShmemSegHdr != NULL);
+	Assert(Segments[shmem_segment].ShmemSegHdr != NULL);
 
-	newStart = ShmemSegHdr->freeoffset;
+	newStart = Segments[shmem_segment].ShmemSegHdr->freeoffset;
 
 	newFree = newStart + size;
-	if (newFree > ShmemSegHdr->totalsize)
+	if (newFree > Segments[shmem_segment].ShmemSegHdr->totalsize)
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
 				 errmsg("out of shared memory (%zu bytes requested)",
 						size)));
-	ShmemSegHdr->freeoffset = newFree;
+	Segments[shmem_segment].ShmemSegHdr->freeoffset = newFree;
 
-	newSpace = (char *) ShmemBase + newStart;
+	newSpace = (char *) Segments[shmem_segment].ShmemBase + newStart;
 
 	Assert(newSpace == (void *) MAXALIGN(newSpace));
 
@@ -273,7 +305,13 @@ ShmemAllocUnlocked(Size size)
 bool
 ShmemAddrIsValid(const void *addr)
 {
-	return (addr >= ShmemBase) && (addr < ShmemEnd);
+	return ShmemAddrIsValidInSegment(addr, MAIN_SHMEM_SEGMENT);
+}
+
+bool
+ShmemAddrIsValidInSegment(const void *addr, int shmem_segment)
+{
+	return (addr >= Segments[shmem_segment].ShmemBase) && (addr < Segments[shmem_segment].ShmemEnd);
 }
 
 /*
@@ -334,6 +372,18 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 			  long max_size,	/* max size of the table */
 			  HASHCTL *infoP,	/* info about key and bucket size */
 			  int hash_flags)	/* info about infoP */
+{
+	return ShmemInitHashInSegment(name, init_size, max_size, infoP, hash_flags,
+							   MAIN_SHMEM_SEGMENT);
+}
+
+HTAB *
+ShmemInitHashInSegment(const char *name,		/* table string name for shmem index */
+			  long init_size,		/* initial table size */
+			  long max_size,		/* max size of the table */
+			  HASHCTL *infoP,		/* info about key and bucket size */
+			  int hash_flags,		/* info about infoP */
+			  int shmem_segment) 	/* in which segment to keep the table */
 {
 	bool		found;
 	void	   *location;
@@ -350,9 +400,9 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
 	hash_flags |= HASH_SHARED_MEM | HASH_ALLOC | HASH_DIRSIZE;
 
 	/* look it up in the shmem index */
-	location = ShmemInitStruct(name,
+	location = ShmemInitStructInSegment(name,
 							   hash_get_shared_size(infoP, hash_flags),
-							   &found);
+							   &found, shmem_segment);
 
 	/*
 	 * if it already exists, attach to it rather than allocate and initialize
@@ -385,6 +435,13 @@ ShmemInitHash(const char *name,		/* table string name for shmem index */
  */
 void *
 ShmemInitStruct(const char *name, Size size, bool *foundPtr)
+{
+	return ShmemInitStructInSegment(name, size, foundPtr, MAIN_SHMEM_SEGMENT);
+}
+
+void *
+ShmemInitStructInSegment(const char *name, Size size, bool *foundPtr,
+					  int shmem_segment)
 {
 	ShmemIndexEnt *result;
 	void	   *structPtr;
@@ -393,7 +450,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	if (!ShmemIndex)
 	{
-		PGShmemHeader *shmemseghdr = ShmemSegHdr;
+		PGShmemHeader *shmemseghdr = Segments[shmem_segment].ShmemSegHdr;
 
 		/* Must be trying to create/attach to ShmemIndex itself */
 		Assert(strcmp(name, "ShmemIndex") == 0);
@@ -416,7 +473,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 			 * process can be accessing shared memory yet.
 			 */
 			Assert(shmemseghdr->index == NULL);
-			structPtr = ShmemAlloc(size);
+			structPtr = ShmemAllocInSegment(size, shmem_segment);
 			shmemseghdr->index = structPtr;
 			*foundPtr = false;
 		}
@@ -433,8 +490,8 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		LWLockRelease(ShmemIndexLock);
 		ereport(ERROR,
 				(errcode(ERRCODE_OUT_OF_MEMORY),
-				 errmsg("could not create ShmemIndex entry for data structure \"%s\"",
-						name)));
+				 errmsg("could not create ShmemIndex entry for data structure \"%s\" in segment %d",
+						name, shmem_segment)));
 	}
 
 	if (*foundPtr)
@@ -459,7 +516,7 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 		Size		allocated_size;
 
 		/* It isn't in the table yet. allocate and initialize it */
-		structPtr = ShmemAllocRaw(size, &allocated_size);
+		structPtr = ShmemAllocRawInSegment(size, &allocated_size, shmem_segment);
 		if (structPtr == NULL)
 		{
 			/* out of memory; remove the failed ShmemIndex entry */
@@ -478,14 +535,13 @@ ShmemInitStruct(const char *name, Size size, bool *foundPtr)
 
 	LWLockRelease(ShmemIndexLock);
 
-	Assert(ShmemAddrIsValid(structPtr));
+	Assert(ShmemAddrIsValidInSegment(structPtr, shmem_segment));
 
 	Assert(structPtr == (void *) CACHELINEALIGN(structPtr));
 
 	return structPtr;
 }
 
-
 /*
  * Add two Size values, checking for overflow
  */
@@ -542,10 +598,11 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 
 	/* output all allocated entries */
 	memset(nulls, 0, sizeof(nulls));
+	/* XXX: take all shared memory segments into account. */
 	while ((ent = (ShmemIndexEnt *) hash_seq_search(&hstat)) != NULL)
 	{
 		values[0] = CStringGetTextDatum(ent->key);
-		values[1] = Int64GetDatum((char *) ent->location - (char *) ShmemSegHdr);
+		values[1] = Int64GetDatum((char *) ent->location - (char *) Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr);
 		values[2] = Int64GetDatum(ent->size);
 		values[3] = Int64GetDatum(ent->allocated_size);
 		named_allocated += ent->allocated_size;
@@ -557,15 +614,15 @@ pg_get_shmem_allocations(PG_FUNCTION_ARGS)
 	/* output shared memory allocated but not counted via the shmem index */
 	values[0] = CStringGetTextDatum("<anonymous>");
 	nulls[1] = true;
-	values[2] = Int64GetDatum(ShmemSegHdr->freeoffset - named_allocated);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset - named_allocated);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
 	/* output as-of-yet unused shared memory */
 	nulls[0] = true;
-	values[1] = Int64GetDatum(ShmemSegHdr->freeoffset);
+	values[1] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	nulls[1] = false;
-	values[2] = Int64GetDatum(ShmemSegHdr->totalsize - ShmemSegHdr->freeoffset);
+	values[2] = Int64GetDatum(Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->totalsize - Segments[MAIN_SHMEM_SEGMENT].ShmemSegHdr->freeoffset);
 	values[3] = values[2];
 	tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc, values, nulls);
 
@@ -630,7 +687,12 @@ pg_get_shmem_allocations_numa(PG_FUNCTION_ARGS)
 	 * this is not very likely, and moreover we have more entries, each of
 	 * them using only fraction of the total pages.
 	 */
-	shm_total_page_count = (ShmemSegHdr->totalsize / os_page_size) + 1;
+	for(int segment = 0; segment < ANON_MAPPINGS; segment++)
+	{
+		PGShmemHeader *shmhdr = Segments[segment].ShmemSegHdr;
+		shm_total_page_count += (shmhdr->totalsize / os_page_size) + 1;
+	}
+
 	page_ptrs = palloc0(sizeof(void *) * shm_total_page_count);
 	pages_status = palloc(sizeof(int) * shm_total_page_count);
 
diff --git a/src/backend/storage/lmgr/lwlock.c b/src/backend/storage/lmgr/lwlock.c
index 46f44bc4511..a36b08895c8 100644
--- a/src/backend/storage/lmgr/lwlock.c
+++ b/src/backend/storage/lmgr/lwlock.c
@@ -80,6 +80,8 @@
 #include "pg_trace.h"
 #include "pgstat.h"
 #include "port/pg_bitutils.h"
+#include "postmaster/postmaster.h"
+#include "storage/pg_shmem.h"
 #include "storage/proc.h"
 #include "storage/proclist.h"
 #include "storage/procnumber.h"
@@ -618,10 +620,15 @@ LWLockNewTrancheId(void)
 	int		   *LWLockCounter;
 
 	LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
-	/* We use the ShmemLock spinlock to protect LWLockCounter */
-	SpinLockAcquire(ShmemLock);
+	/*
+	 * We use the ShmemLock spinlock to protect LWLockCounter.
+	 *
+	 * XXX: Looks like this is the only use of Segments outside of shmem.c,
+	 * it's maybe worth it to reshape this part to hide Segments structure.
+	 */
+	SpinLockAcquire(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 	result = (*LWLockCounter)++;
-	SpinLockRelease(ShmemLock);
+	SpinLockRelease(Segments[MAIN_SHMEM_SEGMENT].ShmemLock);
 
 	return result;
 }
diff --git a/src/include/storage/ipc.h b/src/include/storage/ipc.h
index 3baf418b3d1..6ebda479ced 100644
--- a/src/include/storage/ipc.h
+++ b/src/include/storage/ipc.h
@@ -77,7 +77,7 @@ extern void check_on_shmem_exit_lists_are_empty(void);
 /* ipci.c */
 extern PGDLLIMPORT shmem_startup_hook_type shmem_startup_hook;
 
-extern Size CalculateShmemSize(int *num_semaphores);
+extern Size CalculateShmemSize(int *num_semaphores, int shmem_segment);
 extern void CreateSharedMemoryAndSemaphores(void);
 #ifdef EXEC_BACKEND
 extern void AttachSharedMemoryStructs(void);
diff --git a/src/include/storage/pg_sema.h b/src/include/storage/pg_sema.h
index fa6ca35a51f..8ae9637fcd0 100644
--- a/src/include/storage/pg_sema.h
+++ b/src/include/storage/pg_sema.h
@@ -41,7 +41,7 @@ typedef HANDLE PGSemaphore;
 extern Size PGSemaphoreShmemSize(int maxSemas);
 
 /* Module initialization (called during postmaster start or shmem reinit) */
-extern void PGReserveSemaphores(int maxSemas);
+extern void PGReserveSemaphores(int maxSemas, int shmem_segment);
 
 /* Allocate a PGSemaphore structure with initial count 1 */
 extern PGSemaphore PGSemaphoreCreate(void);
diff --git a/src/include/storage/pg_shmem.h b/src/include/storage/pg_shmem.h
index 5f7d4b83a60..2348c59b5a0 100644
--- a/src/include/storage/pg_shmem.h
+++ b/src/include/storage/pg_shmem.h
@@ -25,6 +25,7 @@
 #define PG_SHMEM_H
 
 #include "storage/dsm_impl.h"
+#include "storage/spin.h"
 
 typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 {
@@ -41,6 +42,20 @@ typedef struct PGShmemHeader	/* standard header for all Postgres shmem */
 #endif
 } PGShmemHeader;
 
+typedef struct ShmemSegment
+{
+	PGShmemHeader *ShmemSegHdr; 	/* shared mem segment header */
+	void *ShmemBase; 				/* start address of shared memory */
+	void *ShmemEnd; 				/* end+1 address of shared memory */
+	slock_t    *ShmemLock; 			/* spinlock for shared memory and LWLock
+									 * allocation */
+} ShmemSegment;
+
+/* Number of available segments for anonymous memory mappings */
+#define ANON_MAPPINGS 1
+
+extern PGDLLIMPORT ShmemSegment Segments[ANON_MAPPINGS];
+
 /* GUC variables */
 extern PGDLLIMPORT int shared_memory_type;
 extern PGDLLIMPORT int huge_pages;
@@ -91,4 +106,7 @@ extern bool PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2);
 extern void PGSharedMemoryDetach(void);
 extern void GetHugePageSize(Size *hugepagesize, int *mmap_flags);
 
+/* The main segment, contains everything except buffer blocks and related data. */
+#define MAIN_SHMEM_SEGMENT 0
+
 #endif							/* PG_SHMEM_H */
diff --git a/src/include/storage/shmem.h b/src/include/storage/shmem.h
index c1f668ded95..69663d412c3 100644
--- a/src/include/storage/shmem.h
+++ b/src/include/storage/shmem.h
@@ -29,15 +29,27 @@
 extern PGDLLIMPORT slock_t *ShmemLock;
 struct PGShmemHeader;			/* avoid including storage/pg_shmem.h here */
 extern void InitShmemAccess(struct PGShmemHeader *seghdr);
+extern void InitShmemAccessInSegment(struct PGShmemHeader *seghdr,
+									 int shmem_segment);
 extern void InitShmemAllocation(void);
+extern void InitShmemAllocationInSegment(int shmem_segment);
 extern void *ShmemAlloc(Size size);
+extern void *ShmemAllocInSegment(Size size, int shmem_segment);
 extern void *ShmemAllocNoError(Size size);
 extern void *ShmemAllocUnlocked(Size size);
+extern void *ShmemAllocUnlockedInSegment(Size size, int shmem_segment);
 extern bool ShmemAddrIsValid(const void *addr);
+extern bool ShmemAddrIsValidInSegment(const void *addr, int shmem_segment);
 extern void InitShmemIndex(void);
+extern void InitVariableShmemIndex(void);
 extern HTAB *ShmemInitHash(const char *name, long init_size, long max_size,
 						   HASHCTL *infoP, int hash_flags);
+extern HTAB *ShmemInitHashInSegment(const char *name, long init_size,
+									long max_size, HASHCTL *infoP,
+									int hash_flags, int shmem_segment);
 extern void *ShmemInitStruct(const char *name, Size size, bool *foundPtr);
+extern void *ShmemInitStructInSegment(const char *name, Size size,
+									  bool *foundPtr, int shmem_segment);
 extern Size add_size(Size s1, Size s2);
 extern Size mul_size(Size s1, Size s2);
 
-- 
2.49.0


--bwrlgp6w2ubxykjq
Content-Type: text/plain; charset=us-ascii
Content-Disposition: attachment;
	filename="v5-0005-Address-space-reservation-for-shared-memory.patch"



^ permalink  raw  reply  [nested|flat] 309+ messages in thread


end of thread, other threads:[~2025-02-28 18:54 UTC | newest]

Thread overview: 309+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2021-09-06 07:54 [PATCH v7] Fix orderby handling in postgres_fdw Ronan Dunklau <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2024-10-09 13:41 [PATCH v1 1/5] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-19 16:43 [PATCH v2 1/6] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v4 1/8] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>
2025-02-28 18:54 [PATCH v5 04/10] Allow to use multiple shared memory mappings Dmitrii Dolgov <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox